{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NIKVUCDP4OEYEYFYJEOAHQFX5S","short_pith_number":"pith:NIKVUCDP","schema_version":"1.0","canonical_sha256":"6a155a086fe3898260b8491c03c0b7ec8a85e02da9d3690e48841b241ce1634b","source":{"kind":"arxiv","id":"1808.09147","version":1},"attestation_state":"computed","paper":{"title":"Toward Fast and Accurate Neural Discourse Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingfeng Yang, Sujian Li, Yizhong Wang","submitted_at":"2018-08-28T07:27:45Z","abstract_excerpt":"Discourse segmentation, which segments texts into Elementary Discourse Units, is a fundamental step in discourse analysis. Previous discourse segmenters rely on complicated hand-crafted features and are not practical in actual use. In this paper, we propose an end-to-end neural segmenter based on BiLSTM-CRF framework. To improve its accuracy, we address the problem of data insufficiency by transferring a word representation model that is trained on a large corpus. We also propose a restricted self-attention mechanism in order to capture useful information within a neighborhood. Experiments on "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1808.09147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T07:27:45Z","cross_cats_sorted":[],"title_canon_sha256":"61c99fbb4749d03956bf87881d417b5e49ccb0f3dec8633eef91353d4731d344","abstract_canon_sha256":"226f7eec7fc5199c6f92268aae43b724508ba651d1a10a96d36638a1aafcc1d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:02.254164Z","signature_b64":"Bx9kejRF/RK7vaK0bodpjgM6NCnCz3GKY4eKK6esDE9QCHK4pprH8umT8pwGBpmLlY67GoVOPtewYRIe7LHeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a155a086fe3898260b8491c03c0b7ec8a85e02da9d3690e48841b241ce1634b","last_reissued_at":"2026-05-18T00:07:02.253535Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:02.253535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Fast and Accurate Neural Discourse Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingfeng Yang, Sujian Li, Yizhong Wang","submitted_at":"2018-08-28T07:27:45Z","abstract_excerpt":"Discourse segmentation, which segments texts into Elementary Discourse Units, is a fundamental step in discourse analysis. Previous discourse segmenters rely on complicated hand-crafted features and are not practical in actual use. In this paper, we propose an end-to-end neural segmenter based on BiLSTM-CRF framework. To improve its accuracy, we address the problem of data insufficiency by transferring a word representation model that is trained on a large corpus. We also propose a restricted self-attention mechanism in order to capture useful information within a neighborhood. Experiments on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09147","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1808.09147","created_at":"2026-05-18T00:07:02.253609+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09147v1","created_at":"2026-05-18T00:07:02.253609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09147","created_at":"2026-05-18T00:07:02.253609+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIKVUCDP4OEY","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIKVUCDP4OEYEYFY","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIKVUCDP","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S","json":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S.json","graph_json":"https://pith.science/api/pith-number/NIKVUCDP4OEYEYFYJEOAHQFX5S/graph.json","events_json":"https://pith.science/api/pith-number/NIKVUCDP4OEYEYFYJEOAHQFX5S/events.json","paper":"https://pith.science/paper/NIKVUCDP"},"agent_actions":{"view_html":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S","download_json":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S.json","view_paper":"https://pith.science/paper/NIKVUCDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09147&json=true","fetch_graph":"https://pith.science/api/pith-number/NIKVUCDP4OEYEYFYJEOAHQFX5S/graph.json","fetch_events":"https://pith.science/api/pith-number/NIKVUCDP4OEYEYFYJEOAHQFX5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S/action/storage_attestation","attest_author":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S/action/author_attestation","sign_citation":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S/action/citation_signature","submit_replication":"https://pith.science/pith/NIKVUCDP4OEYEYFYJEOAHQFX5S/action/replication_record"}},"created_at":"2026-05-18T00:07:02.253609+00:00","updated_at":"2026-05-18T00:07:02.253609+00:00"}